gorkemgoknar
/

wav2vec2-large-xlsr-53-turkish

Automatic Speech Recognition

xlsr-fine-tuning-week

Inference Endpoints

Model card Files Files and versions Community

gorkemgoknar commited on Mar 28, 2021

Commit

d69a18a

•

1 Parent(s): cc4e759

Update README.md

Files changed (1) hide show

README.md +3 -3

README.md CHANGED Viewed

@@ -37,8 +37,8 @@ import torchaudio
 from datasets import load_dataset
 from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
 test_dataset = load_dataset("common_voice", "tr", split="test[:2%]")
-processor = Wav2Vec2Processor.from_pretrained("ozcangundes/wav2vec2-large-xlsr-53-turkish")
-model = Wav2Vec2ForCTC.from_pretrained("ozcangundes/wav2vec2-large-xlsr-53-turkish")
 resampler = torchaudio.transforms.Resample(48_000, 16_000)
 # Preprocessing the datasets.
 # We need to read the aduio files as arrays
@@ -69,7 +69,7 @@ model = Wav2Vec2ForCTC.from_pretrained("ozcangundes/wav2vec2-large-xlsr-53-turki
 model.to("cuda")
 #Note: Not ignoring "'"  on this one
-chars_to_ignore_regex = '[\\,\\?\\.\\!\\-\\;\\:\\"\\“\\%\\‘\\”\\�]'
 resampler = torchaudio.transforms.Resample(48_000, 16_000)
 # Preprocessing the datasets.

 from datasets import load_dataset
 from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
 test_dataset = load_dataset("common_voice", "tr", split="test[:2%]")
+processor = Wav2Vec2Processor.from_pretrained("gorkemgoknar/wav2vec2-large-xlsr-53-turkish")
+model = Wav2Vec2ForCTC.from_pretrained("gorkemgoknar/wav2vec2-large-xlsr-53-turkish")
 resampler = torchaudio.transforms.Resample(48_000, 16_000)
 # Preprocessing the datasets.
 # We need to read the aduio files as arrays
 model.to("cuda")
 #Note: Not ignoring "'"  on this one
+chars_to_ignore_regex = '[\\\\,\\\\?\\\\.\\\\!\\\\-\\\\;\\\\:\\\\"\\\\“\\\\%\\\\‘\\\\”\\\\�]'
 resampler = torchaudio.transforms.Resample(48_000, 16_000)
 # Preprocessing the datasets.